Crm funnel analysis

Skill duandigi/duandigi-growth-marketing-skill/skills/crm-funnel-analysis

Evidence-first AI Agent Skills for growth marketing — multi-channel analytics (SEO, paid media, social, local search, CRM), secure account integration, AI evaluation, experimentation & approval-safe optimization for Claude Code.

Install

npx -y skills add duandigi/duandigi-growth-marketing-skill --skill crm-funnel-analysis

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

25 days oldThe repository was created 25 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use this skill when analyzing lead capture, qualification, response time, pipeline stages, sales outcomes, retention, reactivation, source quality, revenue, and CRM data integrity.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.6 KB, as published. Nobody here has run it

Crm Funnel Analysis

Purpose

Connect marketing activity to qualified leads, customers, revenue, retention, and operational follow-up rather than stopping at form or platform conversions.

Inputs

Lead, contact, account, deal, stage, owner, activity, outcome, and revenue records
Source, campaign, landing-page, content, and tracking identifiers
Qualification criteria, SLA, sales process, loss reasons, and retention definitions
Consent, privacy, deduplication, and identity-resolution rules

If a required input is unavailable, label it unknown, state how it limits the decision, and create a collection, mapping, validation, or instrumentation task. Never invent credentials, assets, metrics, permissions, or business outcomes.

Workflow

Validate stage definitions, mandatory fields, deduplication, source capture, timestamps, and outcome completeness.
Map the funnel from contact through qualification, consultation, proposal, win, repeat, and referral as applicable.
Analyze conversion, velocity, response time, aging, owner performance, loss reasons, source quality, revenue, and retention.
Identify lead leakage, stale records, missing follow-up, stage inflation, source loss, and channel-quality differences.
Compare cohorts by source, landing page, campaign, service, segment, location, and time.
Separate marketing quality, sales execution, capacity, pricing, and product or service fit explanations.
Recommend instrumentation, routing, nurturing, follow-up, offer, qualification, or acquisition changes.

Required output

Return a concise, decision-oriented result containing:

CRM data-quality and funnel summary
Stage conversion, velocity, leakage, and source-quality findings
Revenue, retention, and loss-reason analysis
Operational and attribution limitations
Prioritized CRM, sales, and marketing actions

Label material statements as confirmed, calculated, inferred, assumed, or unknown. Include the data period, last complete period, source lineage, and confidence whenever they can change the decision.

Guardrails

Do not expose personally identifiable lead data in analysis outputs.
Do not contact leads or change stages automatically without authorization and consent rules.
Do not judge a marketing channel solely by raw lead count.
Do not interpret missing loss reasons as customer objections.
Do not claim guaranteed growth or present an estimate as observed fact.
Do not reveal secrets, personal data, private provider payloads, or cross-project information.
When an action can spend money, publish, contact people, alter access, modify production, or delete data, prepare an approval request instead of executing automatically.

Completion check

Before finishing, verify that the output:

answers a specific business or implementation decision;
uses the correct organization, project, asset, date range, time zone, and currency;
separates performance problems from data, connection, and attribution problems;
includes evidence, uncertainty, affected scope, and a measurable next step;
respects least privilege, approval, audit, and rollback requirements;
is no longer than necessary for the decision.